Skills/PyPI/token-save-mcp

token-save-mcp@0.4.1

VERIFIED· not started

Publisher claims: "MCP server that keeps large files out of your coding agent's context by delegating reads to a cheap worker model. Enforced by a hook, measured per call." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher habartru · publishing for 63 daysInstalls 167Last detonated 1 h ago
$claude mcp add token-save-mcp -- uvx token-save-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
TOKENSAVE_API_KEYTOKENSAVE_BASE_URLTOKENSAVE_HOOK_MODETOKENSAVE_LEDGERTOKENSAVE_LOG_DIRTOKENSAVE_MAX_CONCURRENCYTOKENSAVE_MAX_CORPUS_BYTESTOKENSAVE_MAX_RETRIESTOKENSAVE_MIN_LINESTOKENSAVE_MODELTOKENSAVE_NO_LEDGERTOKENSAVE_PROVIDERTOKENSAVE_TIMEOUT
Where it talks to
no vendor host named in the codeAlso ollama.com, openrouter.ai, deepseek.com, groq.com, shields.io — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names ollama.com, openrouter.ai, deepseek.com, groq.com, shields.io as well as its own vendor. The guard injects TOKENSAVE_API_KEY, TOKENSAVE_BASE_URL, TOKENSAVE_HOOK_MODE, TOKENSAVE_LEDGER, TOKENSAVE_LOG_DIR, TOKENSAVE_MAX_CONCURRENCY, TOKENSAVE_MAX_CORPUS_BYTES, TOKENSAVE_MAX_RETRIES, TOKENSAVE_MIN_LINES, TOKENSAVE_MODEL, TOKENSAVE_NO_LEDGER, TOKENSAVE_PROVIDER, TOKENSAVE_TIMEOUT only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx token-save-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Privileged sudo command.github/workflows/ci.yml:40 · Privileged sudo command — agent may execute with elevated privilegeselse sudo apt-get update && sudo apt-get install -y jq; fiFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_server.py:26 · Dynamic module loadingS = importlib.util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Image alt text carrying instructionsREADME.md:19 · Image alt text carrying instructionstoken-save-mcp in actionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:56 · Collapsed <details> block carrying instructions<summary><b>What if I have no API key?</b></summary> `init` will show you this: ``` This tool sends files to a worker model of YOUR choosing. Nothing is connectFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/token_save_mcp/cli.py:178 · Python subprocess execution detectedres = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_cli.py:20 · Dynamic module loading (importlib.loader.exec_module via provenance)_spec.loader.exec_module(C)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/token_save_mcp/cli.py:381 · Python subprocess execution detectedres = subprocess.run(["claude", "mcp", "list"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_cli.py:19 · Dynamic module loadingC = importlib.util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_server.py:27 · Dynamic module loading (importlib.loader.exec_module via provenance)_spec.loader.exec_module(S)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈75 tok
1 file · 17 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for token-save-mcp@0.4.1 as of 28 min ago. This is the package itself, not its dependencies.

token-save-mcp@0.4.1 safety verdict: Verified (not started) — KillerSkills